Real-Time Detection of Banking Fraud Using Predictive Machine Learning Techniques

  • Unique Paper ID: 177212
  • Volume: 11
  • Issue: 8
  • PageNo: 3561-3565
  • Abstract:
  • Financial fraud refers to the act of gaining monetary benefits through dishonest and illegal practices. In recent years, it has emerged as a major threat to businesses and organizations. Despite multiple efforts aimed at mitigating financial fraud, it continues to inflict significant damage on both the economy and society, with daily financial losses reaching substantial levels. Initial fraud detection techniques were introduced several years ago; however, most traditional approaches were manual in nature, making them inefficient, costly, and prone to inaccuracies. Although ongoing research attempts to develop better solutions, the problem of financial fraud remains largely unresolved. Traditional methods, such as manual verifications and audits, are often inaccurate, labor-intensive, and expensive. With the advancement of artificial intelligence, it is now possible to leverage machine learning techniques to analyze large volumes of financial data and effectively detect fraudulent activities. Therefore, this study proposes a new model for fraud detection in bank transactions, utilizing the Random Forest Classifier Machine Learning Algorithm. Using the Banksim dataset, our model demonstrates superior performance compared to existing systems, achieving 99% accuracy in both training and testing phases.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 8
  • PageNo: 3561-3565

Real-Time Detection of Banking Fraud Using Predictive Machine Learning Techniques

Related Articles